LatentKeypointGAN: Controlling GANs via Latent Keypoints

Xingzhe He, Bastian Wandt, Helge Rhodin

Keywords: Part Disentanglement, Unsupervised Learning

Abstract: Generative adversarial networks (GANs) have attained photo-realistic quality in image generation. However, how to best control the image content remains an open challenge. We introduce LatentKeypointGAN, a two-stage GAN which is trained end-to-end on the classical GAN objective with internal conditioning on a set of space keypoints. These keypoints have associated appearance embeddings that respectively control the position and style of the generated objects and their parts. A major difficulty that we address with suitable network architectures and training schemes is disentangling the image into spatial and appearance factors without domain knowledge and supervision signals. We demonstrate that LatentKeypointGAN provides an interpretable latent space that can be used to re-arrange the generated images by re-positioning and exchanging keypoint embeddings, such as generating portraits by combining the eyes, nose, and mouth from different images. In addition, the explicit generation of keypoints and matching images enables a new, GAN-based method for unsupervised keypoint detection.

One-sentence Summary: A GAN that controls the image content via latent keypoints that are learned without supervision, thereby internally disentangling the image into parts.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2103.15812/code)